Gemma 4 E4B VRAM requirements

How much VRAM does Gemma 4 E4B need?

Gemma 4 E4B needs 5.64 GB at Q4_K_M, 9.38 GB at Q8_0 and 17.1 GB at FP16 with 8,192 tokens of context and one request. Each total below is the weights plus the FP16 KV cache and the runtime overhead (0.5 GB plus 10%), and each row opens the calculator with that setting. What the GGUF names mean.

Fine-tuning Gemma 4 E4B? Gemma 4 E4B VRAM for LoRA, QLoRA and full training.

Gemma 4 E4B GGUF files on Hugging Face

The 8 GGUF files llama.cpp picks for Gemma 4 E4B with -hf <repo>:<QUANT>, with the bytes the Hugging Face file list reported on 2026-09-29. Each total is that file plus the FP16 KV cache and 0.5 GB + 10%, one request. "vs estimate" compares the file with the bits-per-weight size the table above uses.

GB here is GiB (1024³ bytes), as everywhere on this site; Hugging Face shows the Q4_K_M file as 5.0 GB, in 10⁹ bytes.

Which Gemma 4 E4B GGUF fits a 16, 24, 32, 48 or 80 GB GPU or a Mac

From the file sizes above: the largest file that fits each machine with an 8K context and 0.5 GB left free, the longest context it then has room for, and the longest context for Q4_K_M (4.64 GB). One request, FP16 KV cache, -np 1.

Run Gemma 4 E4B with llama.cpp or Ollama

llama-server -hf unsloth/gemma-4-E4B-it-GGUF:Q4_K_M -c 131072 -np 1

gemma-4-E4B-it-Q4_K_M.gguf, 5.0 GB, from unsloth/gemma-4-E4B-it-GGUF (checked 2026-09-29). On a 24 GB RTX 3090 / 4090, Q4_K_M with -c 131072 takes 7.84 GB and leaves 16.2 GB. -np 1: one slot, so one 512-token window.

ollama run gemma4:e4b

Ollama library tag gemma4:e4b; its quant is Ollama's choice. Same context: /set parameter num_ctx 131072.

Gemma 4 E4B at 8K, 32K and 128K (full) tokens of context

4 of its 42 layers use full attention, 20 keep a sliding window of 512 tokens and 18 reuse the cache of earlier layers. Each extra token of context adds 16 KB of FP16 cache per request once the sliding windows are full. The last column is the smallest setup here, one card or a group, that holds it at Q4_K_M. How the KV cache works.

How fast Gemma 4 E4B writes

Tokens per second for one request with 8,192 tokens of context, estimated from memory bandwidth. A dash means it does not fit on one card. Try other settings in the speed calculator.

Longest context on one GPU

How many tokens of context Gemma 4 E4B fits on a single card with one request, an FP16 KV cache and 0.5 GB left free. "Full" means the model's whole context window fits.

Model details

Parameters

8.0B (7,996,156,490)

Layers

4 of its 42 layers use full attention, 20 keep a sliding window of 512 tokens and 18 reuse the cache of earlier layers

Attention cache

2 KV heads × 512

Sliding-window layers

2 KV heads × 256

Context length

131,072 tokens

Published weights

14.9 GB (BF16)

On Hugging Face

google/gemma-4-E4B-it

Reported benchmarks

GPQA Diamond 58.6 · MMLU-Pro 69.4 · LiveCodeBench v6 52.0. Vendor-reported: from the maker’s own model card, not rerun here; read 2026-09-30.

Gemma 4 E4B next to similar-sized models

The three models here closest to it in parameter count, at Q4_K_M with 8,192 tokens of context.